Sökning: "Q-Learning"

Visar resultat 16 - 20 av 95 uppsatser innehållade ordet Q-Learning.

  1. 16. Modelling Cyber Security of Networks as a Reinforcement Learning Problem using Graphs : An Application of Reinforcement Learning to the Meta Attack Language

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Sandor Berglund; [2022]
    Nyckelord :Attack graphs; reinforcement learning; graph neural networks; Meta Attack Language; MAL; deepQ-learning DQN ; Attackgrafer; förstärningsinlärning; artificiella neuronnät; grafneuronnät; djup Qinlärning; Meta Attack Language; MAL;

    Sammanfattning : ICT systems are part of the vital infrastructure in today’s society. These systems are under constant threat and efforts are continually being put forth by cyber security experts to protect them. By applying modern AI methods, can these efforts both be improved and alleviated of the cost of expert work. LÄS MER

  3. 17. Exploring the parameter space of Q-learning for faster convergence using Snake

    Kandidat-uppsats, KTH/Datavetenskap

    Författare :Anders Blomqvist; Christian Andersson; [2022]
    Nyckelord :;

    Sammanfattning : In this paper we explore the field of reinforcement learning which has proven to be successful at solving problems of random nature. Such problems can be video games, for example the classical game of Snake. LÄS MER

  4. 18. Reinforcement Learning for Smart Data Center

    Master-uppsats, Luleå tekniska universitet/Datavetenskap

    Författare :Noah Weldeab; [2022]
    Nyckelord :;

    Sammanfattning : Data centers are the key infrastructure backbone powering most IT services worldwide. From text messages, streaming services and voice calls to large organizational services and corporate transactions are all made possible because of data centers. As those services keep growing the scale of the data centers worldwide also keeps growing. LÄS MER

  5. 19. Deep Reinforcement Learning for Card Games

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Oscar Tegnér Mohringe; Rayan Cali; [2022]
    Nyckelord :Reinforcement Learning; Deep Q-Learning; Deep Monte-Carlo; Poker;

    Sammanfattning : This project aims to investigate how reinforcement learning (RL) techniques can be applied to the card game LimitTexas Hold’em. RL is a type of machine learning that can learn to optimally solve problems that can be formulated according toa Markov Decision Process. LÄS MER

  7. 20. Training reinforcement learning model with custom OpenAI gym for IIoT scenario

    Kandidat-uppsats, Mittuniversitetet/Institutionen för informationssystem och –teknologi

    Författare :Pontus Norman; [2022]
    Nyckelord :Q-learning. Reinforcement Learning; OpenAI gym; Q-learning. Reinforcement Learning; OpenAI gym;

    Sammanfattning : Denna studie består av ett experiment för att se, som ett test, hur bra det skulle fungera att implementera en industriell gymmiljö för att träna en reinforcement learning modell. För att fastställa det här tränas modellen upprepade gånger och modellen testas. LÄS MER